Harmonica 0.4: a runtime for facilitation blog.harmonica.chat/runtime-for-...

Harmonica 0.4: a runtime for facilitation

Harmonica began as AI interviewer, one conversation at a time. Version 0.4 turns it into a runtime: something that takes a facilitation method and runs it reliably in multiplayer mode.

blog.harmonica.chat

I've been using Open Collective for a long time through web UI, but in the last couple of months I've started accessing more and more tools via their MCPs I couldn't find any mentions of MCP in OC docs or PRs, so I built one myself: github.com/Citizen-Infr...

There's been a lot of talk about the "context layer", the institutional knowledge AI agents need to be effective. But the hardest knowledge is tacit, trapped in people's heads. Our MCP server and /harmonica-chat command let you launch and manage Harmonica sessions that surface it, straight from CLI.

The Context Layer Needs a Facilitator

We need to tap into the institutional knowledge to make AI agents effective. But the most valuable knowledge is tacit: trapped in people's heads, pre-articulation, never written down. How do you surfa...

blog.harmonica.chat

I'm glad Vitalik sees potential in "tools like Polis" and acknowledges deliberative democracy can't be "installed like a USB drive". Our gov/acc research with @metagov.bsky.social is exploring various challenges and paths forward: blog.harmonica.chat/gov-acc-phas...

What Kind of Governance Infrastructure Web3 Needs?

gov/acc is a Metagov initiative to map the biggest governance challenges in web3 and the solutions emerging to address them. We're sharing preliminary findings from the first Harmonica session, alongs...

blog.harmonica.chat

OSS health audit slash command for Claude Code — based on Producing Open Source Software by Karl Fogel github.com/zhiganov/cla... — shared via My Community (Chrome extension)

GitHub - zhiganov/claude-audit-oss: OSS health audit slash command for Claude Code — based on Producing Open Source Software by Karl Fogel

OSS health audit slash command for Claude Code — based on Producing Open Source Software by Karl Fogel - zhiganov/claude-audit-oss

github.com

Harmonica's 2025 in Review blog.harmonica.chat/looking-back...

End of Year Wrap: 2025 in Review

A year of pivots, partnerships, and hard lessons. From the AI Action Summit to Scroll's Co-Creation Cycle and the Open Facilitation Library, here's what we learned building Harmonica in 2025 — and whe...

blog.harmonica.chat

Remember when the internet wasn't awful? We can go back to that. Some friends and I have released the Resonant Computing Manifesto: a call to bring back such a time, to see if we can bring back a world where technology works for us, rather than against us. resonantcomputing.org

The Resonant Computing Manifesto

Technology should bring out the best in humanity, not the worst—a manifesto for resonant computing built on five principles that reject hyper-scale extraction for human flourishing.

resonantcomputing.org

There is an ongoing war for the soul of "Open-Source". We lost the battle, but we don't have to lose the war. On Dec 3rd, @kpaxle.bsky.social and I are co-hosting a discussion with members of @scenius.bsky.social: @ranganaut.bsky.social, @erlend.sh, and Regis Chapman. RSVP here! luma.com/z9ivf64k

Wednesday! Join me for a Metagov Seminar with my colleague Dr. Orit Peleg from CU Boulder, a computer scientist who does the most wonderful work on self-governance among plants and insects—this is going to be glorious: luma.com/pzbp4zq1?tk=...

Seminar: Governance Among Plants & Insects with Dr. Orit Peleg · Zoom · Luma

Dr. Orit Peleg seeks to understand the behavior of disordered living systems by merging tools from physics, biology, engineering, and computer science. At the…

luma.com

Stuart Lynn from CrownShy talking about some very cool digital democracy projects in Scotland and elsewhere! Nice to see Harmonica mentioned @zhiganov.bsky.social ;)

Yes, and this is why we've created CIBC: to connect builders of citizen infrastructure with local communities all around the 🌎 cibc.notion.site

Citizen Infra Builders Club | Notion

We build, learn, and teach how to use modern tools & protocols that serve mutualism and solidarity.

cibc.notion.site

Anthony Zacharzewski@anthonyzach.be · 10mo ago

Those of us without Muskian resources to build a private luxury bunker need to be putting time and money into the resilience of our democratic and social infrastructure at the grassroots now.

basically, any truly prosocial AI agent should: - be open source - support BYOM (e.g. public AI or locally hosted AI) - be enhanced by prompts & datasets provided by data co-ops - be owned by employees or DAO members - adhere to democratic standards (e.g. democracylevels.org) - what else?

It's weird timing - working on tools for democratic participation while watching actual democracy crumble in real time. But that's exactly why this work matters. When the old systems fail, we need alternatives ready to go. Actual ways for ordinary citizens to govern themselves.

A proposal with policy recommendations for supporting prosocial platforms - governing tech design goes "upstream" as opposed to the "downstream" regulations that govern content. toda.org/assets/files...

As predatory markets tighten their grip and the charade of democracy is abandoned, commons will become even more indispensable. I'm thrilled to say that a significantly revised, updated edition of my book ‘Think Like a Commoner’ is now out, today! Details at thinklikeacommoner.com.

Ooh, nice write-up from Yale! Actually the "AI prototype" is called Harmonica (www.harmonica.chat) — we created a custom workspace for ENS students and built a few RAG pipelines based on MP's facilitators requirements (coming soon to our regular app!)

Yale ISPS@ispsyale.bsky.social · last yr.

On the sidelines of a global AI Summit in Paris, Hélène Landemore helped organize a student assembly to help chart the future of this rapidly evolving technology. bit.ly/41IxM2N @audreyt.org @normalesup.bsky.social @psl-univ.bsky.social @antolw.bsky.social @theophilepenigaud.bsky.social

Emergent Avatars as a Pathway to Global Alignment 1/ Imagine a world where AI helps us align with the planet. Using Harmonica or similar tools, we can create emergent avatars—virtual representatives of stakeholders at different scales. These avatars could help us gradually achieve global alignment.

Excited to soft launch recipe.exchange - a clean, simple way to share recipes on the AT Protocol. No ads, no clutter, just recipes. Post, search, share, and like. You own your data. Still more features to come, but would love early feedback from fellow food enthusiasts! recipe.exchange

Now more than ever, we need collective care. Learn how to resist creatively with Beautiful Solutions: A Toolbox for Liberation, from editors Elandria Williams, Rachel Plattus, Eli Feghali, and @ntnsndr.in. 🔗 https://buff.ly/454B00I

I'm thrilled to announce the first public release of Harmonica, you can start playing on it today 🪗 blog.harmonica.chat/we-are-offic... We're still fixing bugs, but hopefully this early version gives an idea of what we're aiming for.

Harmonica Is in Early Access Now

Big week at Harmonica! In this post we're announcing the first public release of our tool, sharing a couple of updates, and asking for your support in GG22.

blog.harmonica.chat